Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific terms

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ows
    -0.75
    FORMATION
    -0.74
    craft
    -0.73
    chairs
    -0.73
    ãĤ¢ãĥ«
    -0.70
    addr
    -0.69
    strate
    -0.68
    OWS
    -0.67
     constitutes
    -0.66
     develops
    -0.66
    POSITIVE LOGITS
     possibility
    1.27
     obligatory
    1.20
     slightest
    1.20
     usual
    1.19
     occasional
    1.18
     caveat
    1.03
     notion
    1.02
     obvious
    0.96
     temptation
    0.96
     idea
    0.95
    Act Density 0.195%

    No Known Activations